Reexen develops high-performance neural network processors optimized for sensor-end applications. Their processors enable advanced AI capabilities directly on sensor devices, reducing latency and improving efficiency for real-time data processing.
Funding
Funding not disclosed
Founders
Product
Problem
Many AI applications, especially those operating at the edge, require significant computational power, leading to high energy consumption and latency when processing data from sensors. Traditional processing architectures often struggle to efficiently handle the demands of real-time data analysis in applications like XR, IoT, autonomous driving, and robotics.
Solution
Reexen develops high-performance, low-power integrated circuits based on a compute-in-memory architecture, optimized for AIoT applications. Their "sensory-computing integrated" chips enable advanced AI capabilities directly on sensor devices, reducing latency and improving efficiency for real-time data processing. By integrating sensing, memory, and processing into a single chip, Reexen's technology minimizes data movement and maximizes energy efficiency, facilitating the deployment of AI at the edge. The chips are designed using mixed-signal techniques and neuromorphic computing principles to achieve high performance with low power consumption.
Target Audience
The primary target audience includes developers and manufacturers of XR devices, IoT solutions, autonomous vehicles, and robotics systems seeking to integrate high-performance, low-power AI capabilities at the edge.
Features
- Compute-in-memory architecture for efficient data processing
- Mixed-signal design for analog-to-digital conversion and computation
- Neuromorphic computing principles inspired by brain-like processing
- High energy efficiency for edge AI applications
- Support for various sensor modalities
- Optimized for XR, IoT, autonomous driving, and robotics applications